metadata
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- danavery/urbansound8K
metrics:
- accuracy
- f1
model-index:
- name: wav2vec2-finetuned-urbansound8k
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: URBAN-SOUND8K
type: danavery/urbansound8K
args: audio-classification
metrics:
- name: Accuracy
type: accuracy
value: 0.9650829994275901
- name: F1
type: f1
value: 0.965058831730144
wav2vec2-finetuned-urbansound8k
This model is a fine-tuned version of facebook/wav2vec2-base on the URBAN-SOUND8K dataset. It achieves the following results on the evaluation set:
- Loss: 0.2672
- Accuracy: 0.9651
- F1: 0.9651
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.6296 | 1.0 | 1747 | 0.9168 | 0.7098 | 0.6543 |
| 0.3658 | 2.0 | 3494 | 0.4589 | 0.8798 | 0.8788 |
| 0.108 | 3.0 | 5241 | 0.4362 | 0.9107 | 0.9102 |
| 0.3019 | 4.0 | 6988 | 0.4455 | 0.9216 | 0.9215 |
| 0.0019 | 5.0 | 8735 | 0.3645 | 0.9433 | 0.9433 |
| 0.0014 | 6.0 | 10482 | 0.3780 | 0.9416 | 0.9417 |
| 0.1803 | 7.0 | 12229 | 0.3196 | 0.9519 | 0.9519 |
| 0.0004 | 8.0 | 13976 | 0.2672 | 0.9651 | 0.9651 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1